Take a look at the new version of this page: [ beta version ]. Tell us what you think.

ABSTRACT

Pre-processing for raster image based document segmentation begins with image thresholding, which is a binarization process separating foreground from background. In this paper, we compare an existing (Otsu), modified existing (Kittler-Illingworth) and simple peak-based thresholding approach on a set of 982 documents for which existing ground truth (full text) is available. We use the output of an open source OCR engine which incorporates an adaptive/dynamic thresholder that can be bypassed by one of the three global thresholds we tested. This allowed comparison of these three approaches in the aggregate. We then used an independently-generated dictionary as a means of characterizing thresholder efficacy. Such an approach, if successful, will provide the means for selecting an optimal thresholder in the absence of a large set of ground truthed documents. Our preliminary findings here indicate that this approach may provide a reliable means for thresholder comparison and eventually preclude the need for time-intensive human ground truthing.

REFERENCES

• 1: Otsu, N. 1979 A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. Vol. SMC-9, No. 1, 62--66.
• 2: J. Kittler , J. Illingworth, Minimum error thresholding, Pattern Recognition, v.19 n.1, p.41-47, Jan./Feb. 1986 [doi>10.1016/0031-3203(86)90030-0]
• 3: Mitchell, B.T. and Gillies, A.M. 1989 A model-based computer vision system for recognizing handwritten ZIP codes. Machine Vision and Applications Vol. 2, 231--243.
• 4: http://code.google.com/p/tesseract-ocr/ on 4 June 2008.
• 5: Rice S., Jenkins F., and Nartker T. 1995 The Fourth Annual Test of OCR Accuracy. Technical Report 95-04,, Information Science Research Institute, University of Nevada, Las Vegas
• 6: Steven J. Simske , David W. Wright , Margaret Sturgill, Meta-algorithmic systems for document classification, Proceedings of the 2006 ACM symposium on Document engineering, October 10-13, 2006, Amsterdam, The Netherlands [doi>10.1145/1166160.1166190]
• 7: http://www.imagemagick.org/ on June 6, 2008.
• 8: http://www.isri.unlv.edu/ISRI/OCRtk on June 6, 2008.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.1 Digitization and Image Capture

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Text processing
  I.7 DOCUMENT AND TEXT PROCESSING
      I.7.5 Document Capture
          Subjects: Scanning; Optical character recognition (OCR)

General Terms:
Algorithms, Experimentation, Verification

Keywords:
Kittler-Illingworth, OCR, accuracy, meta-algorithms, otsu, testing, threshold